本文選題：天然氣負(fù)荷預(yù)測　切入點：支持向量機(jī)　出處：《華東理工大學(xué)》2013年碩士論文　論文類型：學(xué)位論文

【摘要】：天然氣是一種綠色、經(jīng)濟(jì)、高效、便捷、安全環(huán)保的能源,提高天然氣在能源消費結(jié)構(gòu)中的比例,不僅有利于促進(jìn)節(jié)能減排,又能夠促進(jìn)經(jīng)濟(jì)與社會的可持續(xù)發(fā)展,同時天然氣作為一種城市燃?xì)?與人們生活和工業(yè)生產(chǎn)息息相關(guān),是反映人們生活消費水平的一個重要指標(biāo)。因此,科學(xué)的天然氣負(fù)荷預(yù)測不僅僅關(guān)系著天然氣公司的利益問題,同時還關(guān)系著整個天然氣行業(yè)的建設(shè)和發(fā)展,與廣大的人民生活也息息相關(guān)。 本文基于天然氣負(fù)荷預(yù)測的背景、國內(nèi)外研究現(xiàn)狀以及課題意義的研究,分析天然氣負(fù)荷的特點、規(guī)律及與各種影響因素之間的非線性關(guān)系,根據(jù)支持向量機(jī)(SVM)能夠較好地解決非線性、高維數(shù)以及局部極小點等實際問題的優(yōu)勢,本文提出采用支持向量回歸(SVR)方法建立天然氣負(fù)荷預(yù)測模型并進(jìn)入深入研究。首先基于SVR的研究,采用訓(xùn)練誤差的平方代替松弛變量,將不等式約束改進(jìn)為等式約束,進(jìn)而提出最小二乘支持向量回歸(LS-SVR)的天然氣負(fù)荷預(yù)測模型,從而避免求解二次規(guī)劃問題,提高模型訓(xùn)練的速度,但是LS-SVR丟失了SVR的松散性和魯棒性,導(dǎo)致模型精確度產(chǎn)生一定影響,為解決這些問題,又提出基于加權(quán)最小二乘支持向量回歸(WLS-SVR)的天然氣負(fù)荷預(yù)測模型。同時,考慮到模型參數(shù)對于預(yù)測結(jié)果精度的影響也至關(guān)重要,提出利用粒子群算法(PSO)來優(yōu)化WLS-SVR中的參數(shù),得到基于PSO-WLS-SVR的預(yù)測模型,以進(jìn)一步提高預(yù)測精度。 最后,本文使用天然氣1980-2011年的相關(guān)數(shù)據(jù)進(jìn)行研究,分別對基于SVR、WLS-SVR、PSO-WLS-SVR的預(yù)測模型進(jìn)行仿真并比較。仿真結(jié)果表明：WLS-SVR的模型預(yù)測結(jié)果優(yōu)于SVR模型,且PSO-WLS-SVR的預(yù)測模型預(yù)測誤差更小,從而說明PSO進(jìn)行參數(shù)優(yōu)化對提高預(yù)測精度有一定的優(yōu)勢,也說明PSO-WLS-SVR方法具有一定的有效性和優(yōu)越性,由此可以說明基于粒子群算法的最小二乘支持向量回歸預(yù)測方法具有一定的研究價值和社會意義。
[Abstract]:Natural gas is a kind of green, economical, efficient, convenient, safe and environmentally friendly energy. Increasing the proportion of natural gas in energy consumption structure is not only conducive to energy saving and emission reduction, but also to the sustainable development of economy and society. At the same time, as a kind of city gas, natural gas is closely related to people's life and industrial production, and is an important index to reflect people's living consumption level. Scientific natural gas load forecasting is not only related to the interests of natural gas companies, but also related to the construction and development of the entire natural gas industry, and is closely related to the lives of the broad masses of people. Based on the background of natural gas load forecasting, the research status at home and abroad and the significance of the subject, the characteristics, laws and nonlinear relationship between natural gas load and various influencing factors are analyzed in this paper. According to the advantages of support vector machine (SVM), it can solve nonlinear, high dimension and local minima problems. In this paper, the support vector regression (SVR) method is used to establish the natural gas load forecasting model and it is studied deeply. Firstly, based on the research of SVR, the square of the training error is used to replace the relaxation variable, and the inequality constraint is improved to equality constraint. Furthermore, a natural gas load forecasting model based on least squares support vector regression (LS-SVR) is proposed, which avoids solving quadratic programming problems and improves the speed of model training, but LS-SVR loses the looseness and robustness of SVR. In order to solve these problems, a natural gas load forecasting model based on weighted least squares support vector regression (WLS-SVR) is proposed. Considering that the model parameters are also very important to the precision of prediction results, a particle swarm optimization algorithm (PSO) is proposed to optimize the parameters in WLS-SVR and obtain the prediction model based on PSO-WLS-SVR to further improve the prediction accuracy. Finally, using the data of natural gas from 1980 to 2011, this paper simulates and compares the prediction model based on SVR / WLS-SVR / PSO-WLS-SVR respectively. The simulation results show that the prediction result of WLS-SVR is better than that of SVR model, and the prediction error of PSO-WLS-SVR model is smaller. It shows that the parameter optimization of PSO has some advantages to improve the prediction accuracy, and that the PSO-WLS-SVR method has certain effectiveness and superiority. It can be concluded that the least squares support vector regression prediction method based on particle swarm optimization algorithm has certain research value and social significance.
【學(xué)位授予單位】：華東理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號】：TU996.3;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李雅蘭;劉燕;馮軍;邵震宇;賈林;;天然氣負(fù)荷指標(biāo)及用氣規(guī)律的研究[J];城市燃?xì)?2007年02期

2 龍立波;姚建剛;李連結(jié);錢衛(wèi)華;;短期電力負(fù)荷預(yù)測中的數(shù)據(jù)處理技術(shù)[J];電力需求側(cè)管理;2007年01期

3 孟思齊;楊洪耕;;基于灰色生成的卡爾曼濾波短期負(fù)荷預(yù)測[J];電力系統(tǒng)及其自動化學(xué)報;2008年06期

4 張林;羅曉初;徐瑞林;趙理;;基于時間序列的電力負(fù)荷預(yù)測新算法研究[J];電網(wǎng)技術(shù);2006年S2期

5 顧松;需求影響因素與需求法則初探[J];廣西商專學(xué)報;1996年04期

6 劉涵,劉丁,鄭崗,梁炎明,宋念龍;基于最小二乘支持向量機(jī)的天然氣負(fù)荷預(yù)測[J];化工學(xué)報;2004年05期

7 張穎,高中文;基于時間序列和神經(jīng)網(wǎng)絡(luò)的電力系統(tǒng)負(fù)荷預(yù)測[J];哈爾濱理工大學(xué)學(xué)報;2003年01期

8 馬潔;韓蘊韜;李國斌;;基于自回歸模型的船舶姿態(tài)運動預(yù)報[J];艦船科學(xué)技術(shù);2006年03期

9 李明干,孫健利,劉沛;基于卡爾曼濾波的電力系統(tǒng)短期負(fù)荷預(yù)測[J];繼電器;2004年04期

10 王崗;姜杰;唐昆明;張?zhí)?;基于自適應(yīng)雙向加權(quán)最小二乘支持向量機(jī)的超短期負(fù)荷預(yù)測[J];電力系統(tǒng)保護(hù)與控制;2010年19期

相關(guān)博士學(xué)位論文 前1條

1 姜靜清;最小二乘支持向量機(jī)算法及應(yīng)用研究[D];吉林大學(xué);2007年

相關(guān)碩士學(xué)位論文 前3條

1 凌愛軍;天然氣消費預(yù)測研究[D];西南石油學(xué)院;2002年

2 劉丹;天然氣消費需求量預(yù)測方法改進(jìn)研究[D];重慶大學(xué);2006年

3 李慶生;武漢市城市天然氣負(fù)荷預(yù)測和調(diào)峰方式優(yōu)化[D];華中科技大學(xué);2006年

，

本文編號：1590798